[add]add whisper sdpa

[SangChengC]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @SangChengC, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request integrates PyTorch's Scaled Dot Product Attention (SDPA) into the Whisper model's attention mechanism. By introducing a dedicated SDPA attention class and updating the encoder layer to use it, the change aims to leverage optimized kernels for potentially significant performance improvements and efficiency gains in the Whisper model.

Highlights

• New SDPA Attention Class: A new class, WhisperSdpaAttention, has been introduced. This class extends WhisperAttention and implements its forward method using torch.nn.functional.scaled_dot_product_attention for optimized performance.
• Encoder Layer Integration: The WhisperEncoderLayer has been updated to utilize the newly added WhisperSdpaAttention class for its self_attn mechanism, replacing the previous WhisperAttention implementation.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request introduces WhisperSdpaAttention, an optimized version of the attention mechanism for the Whisper model that uses torch.nn.functional.scaled_dot_product_attention (SDPA). This change is aimed at improving performance. The new attention class is correctly implemented and integrated into the WhisperEncoderLayer. The logic properly handles the nuances of SDPA, such as implicit query scaling and providing a fallback for unsupported features. Overall, the changes are well-executed. I have one minor suggestion to improve code clarity.